Liquid AI2.69BQ4_K_M 下约 2 GB 显存

LFM2.5 2.6B — 显存、速度与本地部署

作者: Jakub Rusinowski · 最后更新:

Liquid AI's on-device agentic model: 2.69B parameters over 30 layers, of which only 8 are attention — the other 22 are double-gated short convolutions that cache nothing. That is why its KV cache stays small at a 128K context where a conventional 2.7B model's would not. Trained on 34T tokens, post-trained for tool calling.

LFM2.5 2.6B 在 Q4_K_M 下约需 2 GB 显存——量化权重加框架开销,不含 KV 缓存。在 Apple Silicon 上,这部分来自统一内存。

逻辑68
创意62
编程60

按量化级别的显存与速度

计算基准:NVIDIA RTX 4090 (24 GB)。仅含权重与开销:该模型架构未公开,因此未计入 KV 缓存。

量化显存速度(估算)适配
Q2_K
2.63 bpw
1.7 GB~253 tok/s可运行
Q3_K_M
3.41 bpw
1.9 GB~233 tok/s可运行
Q4_K_M
4.83 bpw
2.4 GB~203 tok/s可运行
Q5_K_M
5.67 bpw
2.7 GB~189 tok/s可运行
Q6_K
6.56 bpw
3 GB~176 tok/s可运行
Q8_0
8.50 bpw
3.7 GB~152 tok/s可运行
F16
16.00 bpw
6.2 GB~101 tok/s可运行

黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型,详见 方法说明页. LFM2.5 2.6B 显存计算器 →

运行 LFM2.5 2.6B

目录中能运行 LFM2.5 2.6B 的最便宜 GPU 是 Intel Arc B570 (10 GB).

购买此硬件 Intel Arc B570 10GB — 10 GB VRAM · 150 W board power立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07

或在 Vast.ai 比较,低至 $0.35/小时 (typical low · varies)

作为亚马逊联盟成员,我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金,您无需额外付费。

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买,LLM Configurator 可能会获得佣金,而你无需支付任何额外费用。作为亚马逊联盟成员(Amazon Associate),LLM Configurator 会从符合条件的购买中获得收益。
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026年价格波动较大——请以当前商品页价格为准。

如何运行 LFM2.5 2.6B

安装 Ollama,然后运行:

ollama run lfm2-5
Hugging Face 上的权重: LiquidAI/LFM2.5-2.6B ↗

规格

Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed.

参数量
2.69 Billion
上下文窗口
131,072
架构
Hybrid (22 conv + 8 GQA)
提供商
Liquid AI
许可证
LFM Open License v1.0
Practical deployment
Edge device (phone, SBC)
规格量化
Q4_K_M
系统内存
8 GB
记录更新于
2026-09-19
许可证LFM Open License v1.0允许商业使用

Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

Commercial use is licensed only below $10M annual revenue; above that, a separate agreement.

质量与使用场景

评分由模型作者或独立评测方发布——衡量质量而非吞吐量,并非我们实测。

最适合on deviceagentstool callingedge

我的 GPU 能运行 LFM2.5 2.6B 吗?

LFM2.5 的其他尺寸

LFM2.5 2.6B — 常见问题

How much VRAM does LFM2.5 2.6B need?

About 2 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does LFM2.5 2.6B run on an RTX 4090 (24 GB)?

Yes. LFM2.5 2.6B needs about 2 GB at Q4_K_M, inside a 24 GB card, at an estimated 203 tokens/sec.

How do I run LFM2.5 2.6B locally?

Install Ollama and run `ollama run lfm2-5`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does LFM2.5 come in?

LFM2.5 2.6B (2 GB), LFM2.5-8B-A1B (6 GB), LFM2.5-24B-A2B (15 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.